Pesquisa Profunda

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Portuguese research workflow with no code execution, credentials, persistence, or hidden high-impact behavior.

Safe to install as a research template. Use it for deeper research tasks where citations and methodology matter, and review important sources yourself, especially for legal, medical, financial, or other high-stakes topics. State your preferred language, region, and scope if you do not want the default Brazilian Portuguese framing.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The skill description is broad and does not define when it should or should not be invoked, which can cause an agent to apply it to unsuitable tasks. In a research-oriented skill, ambiguous activation increases the chance of unnecessary web retrieval, overbroad data handling, or use in contexts where a lighter or safer workflow would be more appropriate.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal